A batch image processing tool that identifies, extracts, and organizes text from multiple images into structured Markdown documents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install test20260402
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install test20260402 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Image Text Extractor?
The Image Text Extractor is a powerful utility within the Openclaw Skills ecosystem designed to automate the conversion of visual data into editable text. It handles batch uploads of images, performing high-fidelity optical character recognition (OCR) while preserving the original document hierarchy. By synthesizing multiple images into a single structured file, it bridges the gap between static captures and dynamic, searchable documentation.
This skill is particularly effective for users who need to digitize large volumes of information from screenshots, slide decks, or printed materials. Unlike standard OCR tools, this implementation within Openclaw Skills ensures that paragraphs, headers, and lists are correctly identified and formatted in Markdown, making the output immediately ready for use in knowledge management systems or development workflows.
Image Text Extractor Use Cases
- Batch converting document screenshots into a single, editable Markdown file.
- Digitizing presentation slides (PPT/Keynote) into structured study or meeting notes.
- Extracting textual data from mixed-language images (Chinese and English).
- Automating the transcription of printed reports captured via mobile devices.
How Image Text Extractor Works
- The user uploads one or multiple images in supported formats such as PNG, JPG, JPEG, GIF, or WebP.
- The skill triggers the read_image tool for each file, applying a specialized prompt to extract all visible text while maintaining formatting.
- Extracted data is organized sequentially, with clear identifiers for each source image (e.g., Image 1, Image 2).
- The system preserves the semantic structure, including titles, lists, and paragraph breaks found in the original images.
- A final Markdown document is generated, containing metadata such as the title, extraction time, and the total count of processed images.
Image Text Extractor Setup
To utilize this skill, ensure your AI agent is equipped with a vision-capable model and the read_image tool. In the Openclaw Skills environment, you can initiate the process by uploading files directly.
# Example: Triggering image extraction via CLI
openclaw run image-text-extractor --files ./path/to/images/
Image Text Extractor Data Schema & Taxonomy
The skill organizes extracted data into a standardized Markdown format as follows:
| Feature | Description |
|---|---|
| Document Title | A descriptive name for the extraction session |
| Extraction Time | The timestamp when the OCR process was completed |
| Image Count | The total number of images included in the batch |
| Content Blocks | Text segmented by image source with original formatting preserved |
| File Output | Optional generation of a .md file for download |
Image Text Extractor Advanced Features
- Multi-image batch processing with strict sequential order retention.
- Automatic detection and preservation of structural elements like headers and bullet points.
- Intelligent error handling that reports failed image recognitions without interrupting the entire batch.
- Native support for mixed-language recognition within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
Aliyun CLI Management
A comprehensive automation skill for managing Alibaba Cloud resources through the official Aliyun Command Line Interface.
Alibaba Cloud SLS Log Query
A powerful AI agent skill for querying, analyzing, and troubleshooting logs within Alibaba Cloud Log Service (SLS) using the Python SDK.
Weekly Report Generator
An intelligent agent skill that automatically analyzes git commit history to generate and distribute professional weekly status reports.
Agent Debate
Agent Debate is a multi-agent framework that improves response accuracy and reduces hallucinations by having multiple AI agents independently answer, critique, and refine solutions through structured disagreement.
opencode AI Coding Orchestrator
A sophisticated orchestration skill designed to delegate code analysis and modification tasks to specialized AI agents while maintaining developer control.
Xiaohongshu Viral Title Generator
A bulk title generation tool that creates viral-style headlines for Xiaohongshu using psychological triggers, templates, and automatic emoji integration.
Featured*
